// Llama · Text LLM
Llama-3.2-3B-Instruct: VRAM & local deployment
3.21B parameters. About 3.6 GB at 4-bit and 8.5 GB at BF16 with one 8K-token request.
released 2024-09-18licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | Meta · meta-llama |
|---|---|
| Family / series | Llama · Llama-3.2 |
| Type | Text LLM (text-generation) |
| Parameters | 3.21B Source: counted from official safetensors weights |
| Context length | 128K tokens (131,072)max_position_embeddings in config.json |
| Architecture | 28 layers · GQA |
| Released weights | BF16 · 6.4 GBdownload |
| Licence | Llama 3.2 Community · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2024-09-18 (Hugging Face repo created) |
| Access | Gated: accept the licence on Hugging Face before downloading. |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 6.4 GB | 8.5 GB | 11.3 GB | 22.6 GB | 12GB GPU | Mac 16GB |
| FP8 / INT8 / Q8_0 | 3.4 GB | 5.2 GB | 8.0 GB | 19.3 GB | 8GB GPU | Mac 16GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 1.9 GB | 3.6 GB | 6.4 GB | 17.7 GB | 8GB GPU | Mac 16GB |
KV cache per request: 8K 0.9 GB · 32K 3.8 GB · 128K 15.0 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- Ollama — in the official Ollama library · llama3.2:3b
ollama run llama3.2:3b04Official repositories & quantised builds
4 official repo(s) from meta-llama.
- Llama-3.2-3B-Instruct Instruct
- Llama-3.2-3B main
- Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 Instruct/INT4
- Llama-3.2-3B-Instruct-QLORA_INT4_EO8 Instruct/INT4
05Other Llama models
All 16 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Llama-3.2-1B-Instruct · same series | 1.24B | 1.6 GB | 2024-09-18 |
| Llama-Prompt-Guard-2-22M | 71M | 0.5 GB | 2025-04-28 |
| Llama-Prompt-Guard-2-86M | 279M | 0.7 GB | 2025-04-28 |
| Llama-Guard-4-12B | 12B | 8.5 GB | 2025-04-23 |
| Llama-4-Scout-17B-16E-Instruct | 108.6B | 73.0 GB | 2025-04-02 |
| Llama-4-Maverick-17B-128E-Instruct | 401.6B | 268 GB | 2025-04-01 |
| Llama-3.3-70B-Instruct | 70.6B | 50.2 GB | 2024-11-26 |
| Llama-Guard-3-1B | 1.5B | 1.5 GB | 2024-09-20 |
| Llama-Guard-3-11B-Vision | 10.7B | 7.6 GB | 2024-09-20 |
06Sources
Data checked 2024-10-24. Parameters, context and licence are copied from the official repository; memory figures are our estimates.